import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns



df=pd.read_csv("idman_dataset.csv")

df.head()




df.isnull().sum()


df.columns = ['Year', 'Unnamed', 'Sports_Facilities', 'People_Doing_Sports_K']

df = df.drop('Unnamed', axis=1)


print(df.isnull().sum())
        
df = df.sort_values('Year')

df

Year                     0
Sports_Facilities        0
People_Doing_Sports_K    0
dtype: int64

plt.figure(figsize=(10, 6))
plt.plot(df['Year'], df['Sports_Facilities'])
plt.title('Number of Sports Facilities Over Time')
plt.xlabel('Year')
plt.ylabel('Number of Facilities')
plt.grid(True)
plt.show()

fig, ax1 = plt.subplots(figsize=(12, 6))


ax1.plot(df['Year'], df['Sports_Facilities'], 'b-o')
ax1.set_xlabel('Year')
ax1.set_ylabel('Sports Facilities', color='blue')


ax2 = ax1.twinx()
ax2.plot(df['Year'], df['People_Doing_Sports_K'], 'r-s')
ax2.set_ylabel('People(thousands)', color='red')

plt.title('Sports Facilities vs Participation Over Time')
plt.show()

# Make your charts prettier with seaborn
sns.set_style("whitegrid")
# Recreate your charts with seaborn styling

import plotly.graph_objects as go
import plotly.express as px

# Create interactive dual-axis chart
fig = go.Figure()

fig.add_trace(go.Scatter(
    x=df['Year'], 
    y=df['Sports_Facilities'],
    name='Sports Facilities',
    mode='lines+markers'
))

fig.add_trace(go.Scatter(
    x=df['Year'], 
    y=df['People_Doing_Sports_K'],
    name='People Doing Sports (K)',
    mode='lines+markers',
    yaxis='y2'
))

fig.update_layout(
    title='Interactive: Sports Facilities vs Participation',
    yaxis=dict(title='Sports Facilities'),
    yaxis2=dict(title='People (thousands)', overlaying='y', side='right')
)

fig.show()

plt.figure(figsize=(8, 6))
sns.scatterplot(x='Sports_Facilities', y='People_Doing_Sports_K', data=df, s=100)
plt.title('Correlation: Facilities vs Participation')
correlation = df['Sports_Facilities'].corr(df['People_Doing_Sports_K'])
plt.text(0.05, 0.95, f'Correlation: {correlation:.3f}', 
         transform=plt.gca().transAxes, fontsize=12)
plt.show()

plt.figure(figsize=(6, 4))
sns.heatmap(df[['Sports_Facilities', 'People_Doing_Sports_K']].corr(), 
            annot=True, cmap='coolwarm', center=0)
plt.title('Correlation Heatmap')
plt.show()

df['Facilities_Growth'] = df['Sports_Facilities'].pct_change() * 100
df['Participation_Growth'] = df['People_Doing_Sports_K'].pct_change() * 100

plt.figure(figsize=(12, 5))
plt.plot(df['Year'], df['Facilities_Growth'], label='Facilities Growth %', marker='o')
plt.plot(df['Year'], df['Participation_Growth'], label='Participation Growth %', marker='s')
plt.title('Year-over-Year Growth Rates')
plt.xlabel('Year')
plt.ylabel('Growth Rate (%)')
plt.legend()
plt.axhline(y=0, color='black', linestyle='--', alpha=0.3)
plt.grid(True)
plt.show()

df['Facilities_per_1K'] = df['Sports_Facilities'] / df['People_Doing_Sports_K']

fig = px.line(df, x='Year', y='Facilities_per_1K', 
              title='Sports Facilities per 1000 Participants',
              markers=True)
fig.update_layout(yaxis_title='Facilities per 1000 People')
fig.show()

	Year	Sports_Facilities	People_Doing_Sports_K
29	1995	6670.0	394.1
28	1996	6937.0	298.7
27	1997	6885.0	353.4
26	1998	7238.0	329.6
25	1999	7864.0	352.6
24	2000	7908.0	355.2
23	2001	8129.0	400.5
22	2002	8214.0	410.3
21	2003	8940.0	539.6
20	2004	8948.0	546.5
19	2005	8732.0	529.8
18	2006	9000.0	538.4
17	2007	9323.0	539.3
16	2008	9604.0	542.6
15	2009	9623.0	1617.4
14	2010	9491.0	1649.8
13	2011	9954.0	1660.4
12	2012	10259.0	1678.4
11	2013	10574.0	1685.1
10	2014	10798.0	1723.8
9	2015	11027.0	1724.7
8	2016	11215.0	1755.4
7	2017	11412.0	1785.9
6	2018	11545.0	1827.9
5	2019	11674.0	1864.8
4	2020	11770.0	1861.6
3	2021	11915.0	1897.6
2	2022	12156.0	1918.8
1	2023	12270.0	1921.6
0	2024	12290.0	1898.8

1. Steady Infrastructure Growth¶

2. The 2008 Data Anomaly¶

Conclusion¶